See here for detailed event information. RSVP Requested.
ABSTRACT: A shift toward urban and asymmetric warfare is pushing the Army toward distributed autonomous systems. They must be adaptable, mobile, and resilient. Among these are systems of multiple collaborating robots, such as drone swarms. In future missions, humans and autonomous assets will be working in coordinated teams at nearly the same level of authority. The effects of human interaction with automation are often unintuitive and may complicate the design of such systems.
The Army Research Lab's Technology Development and Transition Team (ARL TDT) seeks to solve these issues through the use of agent-based modeling and simulation, to enable prediction of system-of-system performance at early design stages. This enables simulation of different mixtures of humans and autonomous agents spanning the design space of possible systems. As a motivating case study, a model and simulation of a multi-operator, multi-UAV surveillance team is presented. The model of human performance dynamically adjusts for fatigue, workload, and task difficulty. Coupled with physical models of quadcopter and fixed-wing UAVs, this establishes a platform for predicting system capability as a function of human team size, UAV team size, mix of diverse UAV types, and hardware quality.
The simulation can be previewed at https://www.youtube.com/watch?v=IxSaexuccbI
A brief introduction to Army Research Lab - West, established in Playa Vista in 2015 to engage with local universities and industry partners, will also be presented.
BIOGRAPHY: Dr. James Humann is a postdoctoral fellow at the US Army Research Lab. He earned an MS and PhD in Mechanical Engineering from USC, with an emphasis on design and systems engineering, and a BS in Mechanical Engineering from the University of Oklahoma. His current research focuses on agent-based modeling of distributed systems-of-systems including human, manned, and unmanned assets. He is an INCOSE LA member and has presented at CSER and IEEE SysCon.